# Team0

> Team0 plugs into the AI agents a person already uses, so every one of them starts from what's true about their work: their people, commitments and decisions. It builds that understanding from the work they connect and keeps it current. The product is called Living Understanding. It is invite-only during a private beta.

New agent. Same you.

People now use several agents at once and switch when a better one launches. Each agent learns on its own and keeps what it learns to itself. Team0 keeps the understanding on the user's side instead: what is current, what changed and why, what is still unknown, and where every statement came from. Any connected agent reads the same understanding, within the access the user gave that agent.

## How it works, from the user's side

A few minutes to set up. Nothing to maintain. Nothing to rebuild: it plugs into what the user already does.

1. Join: accept an invitation and create an account.
2. Connect sources: start with Google for email and calendar; add Notion, GitHub, Jira, HubSpot or documents at any time. Team0 starts reading right away.
3. Connect agents: each agent the user picks is connected from Team0 and gets its own access, which the user can change at any time.
4. From then on, every agent connected starts from the same understanding of the user's work. Codex, Claude Code, OpenClaw and Hermes read Team0 on their own before they answer. Agents like ChatGPT and Claude decide for themselves when to look, so mentioning Team0 in a request makes sure they do.

## What makes it different from memory or a second brain

Most people start with an agent and a few notes files that it updates after each session. It works at first. Then the files bloat, key details get summarised away, and the story of what actually happened is lost; every agent ends up reading a different version of the user. Team0 does the hard part: it keeps one understanding current, from the work itself, and gives every agent the same one. A new agent knows what the last one did.

A second brain is something you feed and keep tidy. Team0 builds itself from the work you connect, keeps itself current, and lends the result to every agent you use.


- Statements, not summaries: each one is tied to who said it, the exact supporting passage, and its source.
- Two clocks: when something became true is kept separate from when Team0 learned it.
- Nothing is overwritten: a newer statement supersedes an older one, and the older one stays in history.
- A request is not a commitment, something heard is not confirmed, and silence never proves a task was done.
- Unknowns stay visible instead of being filled with a guess.
- One record per person, built conservatively from every source they appear in.
- Corrections are made once and reach every connected agent.

## How an agent should use Team0

Use Team0 when a task depends on current, sourced context about the user's work: preparing for a meeting, carrying a customer decision into a build, picking up work started in another agent, or checking what changed before acting. Do not use Team0 to fetch one raw email or calendar event that the source system can return directly.

1. The user connects the agent in Team0 (Agents, then Connect an agent). Each agent gets its own grant, which the user can stop or revoke at any time.
2. Codex, Claude Code, OpenClaw and Hermes can install the Team0 plugin, which reads before each reply and saves each finished conversation.
3. Any other MCP client connects to the Streamable HTTP server at `https://api.team0.ai/v1/mcp`. Agents that support it sign in to Team0 with OAuth (ChatGPT does); others send their own per-agent key as `Authorization: Bearer t0_live_…`.
4. Main tools: `team0_living_understanding` (a scoped, sourced read of what the request names), `team0_get_evidence`, `team0_replay_understanding`, `team0_explain`, `team0_contribute_conversation` and `team0_share_tool_activity` (saved as evidence under the agent's name, never trusted automatically), and `team0_get_operation`. The tool list an agent sees depends on its grant.
5. Connected agents can also message each other through Team0 (`list_my_agents`, `message_agent`, `check_inbox`). This is on by default and can be switched off per agent; a message waits in the receiving agent's Team0 inbox until it next checks.
6. Agents connected earlier with a `t0c2c_` key at `https://api.team0.ai/mcp/mcp` keep working.

Machine-readable: [OpenAPI](https://team0.ai/openapi.json), [MCP discovery](https://team0.ai/.well-known/mcp.json), [OAuth discovery](https://team0.ai/.well-known/oauth-authorization-server), [scopes](https://team0.ai/.well-known/oauth-protected-resource).

## Agents that work with Team0

Claude Code, Codex, Claude, ChatGPT, OpenClaw, Hermes, Claude Cowork, Town, Lindy, monday.com and Base44. Coming soon: Cursor, Windsurf and n8n.

## Core pages

Every public page has an agent-readable Markdown version at the same address plus `.md` (the homepage's is /index.md). Each page also links to it with `<link rel="alternate" type="text/markdown">`. The links below go to the Markdown versions.

- [Home](https://team0.ai/index.md): what Team0 is, in one scroll.
- [Product](https://team0.ai/product.md): the Living Understanding workspace (Now, Explore, people, what changed, agent activity, sources).
- [How it works](https://team0.ai/how-it-works.md): from connected work to a read an agent can trust, in plain words.
- [The World Model](https://team0.ai/world-model.md): the technical overview: the knowledge stack, where Team0 differs, the system diagram, measurements and limits.
- [Architecture](https://team0.ai/world-model/architecture.md): follow one email through Team0: background ingest, a checked write path, twelve truth checks, a scoped read, a governed door, every connected agent, and what is kept for how long.
- [Data model](https://team0.ai/world-model/data-model.md): typed statements, provenance, holder attribution, two clocks, trusted/evidence/candidate lanes, ontology held as data.
- [Entity resolution](https://team0.ai/world-model/entity-resolution.md): deterministic keys merge, similar names never merge on their own, conflicting addresses split, extracted relationships are re-checked nightly by models from two vendors.
- [Truth maintenance](https://team0.ai/world-model/truth-maintenance.md): state supersession keyed on identity and type, typed reversible verdicts, corrections outrank automation, contradictions resolved by asking.
- [Trust and scope](https://team0.ai/world-model/trust-and-scope.md): support, provenance, relationship and attention kept separate; scope compiled into every query (prevention, not redaction).
- [Understanding Engine](https://team0.ai/world-model/understanding-engine.md): meaning layers, eight retrieval pools, deterministic packets, frozen replayable agent reads.
- [Memory vs understanding](https://team0.ai/memory-vs-understanding.md): how Team0 differs from memory layers such as mem0, OpenMemory, Zep, Letta and Supermemory, described from their own docs.
- [What is a second brain for AI agents?](https://team0.ai/second-brain.md): a plain explainer: why agents need one, what it holds, how agents read and save, the three ways people build one (each agent's own memory, markdown files, a second brain that builds itself) with what each is good at and what to watch for, and six questions to ask of any second brain.
- [Markdown second brain vs Team0](https://team0.ai/markdown-second-brain.md): markdown files are great, a second brain built on them isn't. You trust your AI to keep the files right; six ways it quietly breaks (overwritten, half updated, a guess saved as fact, cut by a summary, never told, out of reach); and how Team0 builds itself and keeps itself current for every agent you connect.
- [Team0 comparisons](https://team0.ai/compare.md): how Team0 compares with Supermemory, Mem0, Letta, Zep, and the memory built into Claude and ChatGPT; each competitor described only in its own published words.
- [Supermemory vs Team0](https://team0.ai/compare/supermemory.md)
- [Mem0 vs Team0](https://team0.ai/compare/mem0.md)
- [Letta vs Team0](https://team0.ai/compare/letta.md)
- [Zep vs Team0](https://team0.ai/compare/zep.md)
- [Claude and ChatGPT memory vs Team0](https://team0.ai/compare/claude-and-chatgpt-memory.md)
- [The 31 problems](https://team0.ai/agentic-understanding.md): everything that has to be solved before an agent can understand someone.
- [Walk through an example](https://team0.ai/example.md): one matter over four days, and what two agents receive.
- [Sources](https://team0.ai/sources.md): every source the understanding learns from.
- [Works with](https://team0.ai/works-with.md): the agents that connect today and those coming soon.
- [Claude Code and Codex](https://team0.ai/claude-code-and-codex.md): switching between Claude Code and Codex without explaining anything twice.
- [Use cases](https://team0.ai/use-cases.md): meeting preparation, decisions carried into builds, picking up in any agent, seeing what changed.
- [Pricing](https://team0.ai/pricing.md): Living Understanding pricing, one plan with no per-agent fees. It is a private beta price, kept for at least 12 months by anyone who subscribes.
- [Developers](https://team0.ai/developers.md): connect agents over MCP or build with the HTTP API.
- [Trust and control](https://team0.ai/trust.md): what users can see, correct, stop and delete.
- [Security](https://team0.ai/security.md): what Team0 keeps and doesn't, isolation, processors, and straight answers.
- [Privacy](https://team0.ai/privacy.md) and [Terms](https://team0.ai/terms.md).
- [What's new](https://team0.ai/whats-new.md): the dated public shipping record.
- [Journal](https://team0.ai/blog.md): essays on how understanding works and what we learned building it.
- [FAQ](https://team0.ai/faq.md): answers to common questions about Living Understanding.
- [About](https://team0.ai/about.md) and [Support](https://team0.ai/support.md): company, founder, and how to reach us (hey@team0.ai).
- [Chief of Staff](https://team0.ai/chief.md): Team0's optional AI chief of staff, which works from the same understanding.

## Team0 Journal

- [Memento's Problem Was Never the Notes](https://team0.ai/blog/agentic-understanding/mementos-problem-was-never-the-notes) — AI agents are like the hero of Memento: they can't form new memories, so they live on notes. Better learning will help. But the notes still have to stay true.
- [AI Agents Need a Living Understanding](https://team0.ai/blog/agentic-understanding/ai-agents-need-living-understanding) — An assistant can find an old email. Can it tell what changed since then? Why Team0 gives agents a way to work from the situation as it stands now.
- [Beyond the Knowledge Base: How a Company Learns to Understand Itself](https://team0.ai/blog/agentic-understanding/beyond-the-knowledge-base-company-understanding) — Search can find the message. It can't always tell whether the work is done, who knows the answer, or what changed. What a Company Brain needs beyond search.
- [The Four Levels of Agentic Understanding](https://team0.ai/blog/agentic-understanding/four-levels-of-agentic-understanding) — Remembering an old answer is easy. Noticing that it stopped being true is harder. Four things an AI assistant needs to do well.
- [Your Agent Needs a Model of Your World, Not a Longer Chat History](https://team0.ai/blog/agentic-understanding/your-agent-needs-a-world-model) — A chat history remembers what was said. It doesn't reliably know which meeting moved, who made a promise, or what changed afterward.
- [A Second Brain You Have to Feed Isn't One](https://team0.ai/blog/building-team0/a-second-brain-you-have-to-feed-isnt-one) — I don't want another system that asks me to maintain folders before it can help me. The lesson that shaped how we're building Team0.
- [Which Promises Are Still Open?](https://team0.ai/blog/world-model-in-practice/a-reminder-is-not-a-commitment) — An email that says “sent” is not always proof of delivery. Here's how Team0 handles a promise it has captured as open work.
- [Your Agents Should Not Each Build a Second Brain](https://team0.ai/blog/world-model-in-practice/one-world-many-agents) — Correct one assistant, and the others may still repeat the mistake. Why Team0 keeps one changing picture of the work and gives each agent only what it may see.
- [Why First Contact Is Not a Relationship](https://team0.ai/blog/world-model-in-practice/truth-is-not-attention) — A stranger's urgent email should not become your top priority just because it arrived today. A mistake we found while building Team0.
- [What Is an AI Chief of Staff?](https://team0.ai/blog/agentic-understanding/what-is-ai-chief-of-staff) — What an AI Chief of Staff should actually do: know what's changed, prepare you for what's next, handle the follow-through and know when to ask.

## Privacy and security

- Each customer's data sits in its own database schema; which account a request may touch is decided by the server.
- Customer content is not used to train anyone's models.
- Team0 is CASA Tier 2 certified. It does not hold SOC 2 and does not claim it.
- Everything runs in one region in the United States.
- Users can see the source of every statement, correct it, remove it, stop an agent or cut it off. Closing an account deletes personal information within 30 days, apart from what the law requires us to keep.

## Canonical summary

Team0 is an understanding layer for the agents people already use. It maintains a sourced, current, correctable model of a person's work and gives each connected agent a scoped read of it, so switching or adding agents never means starting over.